© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 8821
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticisms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    78
    +0.14
    0.8%
    223
    +0.13
    0.7%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.14
    0.03
    223
    +0.13
    0.02
    308
    +0.12
    0.02
    Negative Logits
    rendum
    -1.64
     LICENSE
    -1.60
    orect
    -1.53
    ttp
    -1.52
     Definition
    -1.46
    vez
    -1.41
     ![](
    -1.40
     synthase
    -1.38
     Clerk
    -1.37
    poons
    -1.37
    POSITIVE LOGITS
    time
    1.93
    experience
    1.91
    important
    1.82
    clusive
    1.76
    Ģ
    1.73
    around
    1.71
    heart
    1.70
    American
    1.62
     glory
    1.58
     time
    1.58
    Activations Density 0.093%

    No Known Activations